Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching
This addresses the problem of generating realistic human motions for applications like animation or robotics by incorporating geometric structure, representing a novel method for a known bottleneck.
The paper tackles human motion generation by proposing a Riemannian framework that models motion on a product manifold, achieving state-of-the-art FID scores of 0.043 on HumanML3D and 5.6 on MotionMillion.
Human motion generation is often learned in Euclidean spaces, although valid motions follow structured non-Euclidean geometry. We present Riemannian Motion Generation (RMG), a unified framework that represents motion on a product manifold and learns dynamics via Riemannian flow matching. RMG factorizes motion into several manifold factors, yielding a scale-free representation with intrinsic normalization, and uses geodesic interpolation, tangent-space supervision, and manifold-preserving ODE integration for training and sampling. On HumanML3D, RMG achieves state-of-the-art FID in the HumanML3D format (0.043) and ranks first on all reported metrics under the MotionStreamer format. On MotionMillion, it also surpasses strong baselines (FID 5.6, R@1 0.86). Ablations show that the compact $\mathscr{T}+\mathscr{R}$ (translation + rotations) representation is the most stable and effective, highlighting geometry-aware modeling as a practical and scalable route to high-fidelity motion generation.